论文标题
通过图像分类中的早期停顿，通过神经建筑搜索进行两阶段的体系结构微调
Two-stage architectural fine-tuning with neural architecture search using early-stopping in image classification
论文作者
论文摘要
在许多深层神经网络（DNN）应用中，在行业领域收集高质量数据的困难阻碍了DNN的实际使用。因此，转移学习的概念已经出现，该概念利用了在大规模数据集中训练的DNN的验证知识。因此，本文提出了受神经体系结构搜索（NAS）的启发的两阶段建筑微调。主要思想之一是突变，它使用给定的架构信息降低了搜索成本。此外，还考虑了提前终止搜索过程来降低NAS成本的早期。实验结果验证我们提出的方法可降低32.4％的计算和22.3％的搜索成本。
In many deep neural network (DNN) applications, the difficulty of gathering high-quality data in the industry field hinders the practical use of DNN. Thus, the concept of transfer learning has emerged, which leverages the pretrained knowledge of DNNs trained on large-scale datasets. Therefore, this paper suggests two-stage architectural fine-tuning, inspired by neural architecture search (NAS). One of main ideas is mutation, which reduces the search cost using given architectural information. Moreover, early-stopping is considered which cuts NAS costs by terminating the search process in advance. Experimental results verify our proposed method reduces 32.4% computational and 22.3% searching costs.
